© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21103
    Prev
    Next
    INDEX
    Explanations

    communication skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大å¹ħå¢ŀéķ¿
    -0.08
     Cah
    -0.08
    è½°è½°çĥĪ
    -0.07
    è¿Ľä¸ĢæŃ¥åĬłå¤§
    -0.07
    åĮ»çĶŁå»ºè®®
    -0.07
    isted
    -0.07
    èĩªåĬĽ
    -0.07
    ç§ijåŃ¦å®¶ä»¬
    -0.07
    æľīåħ³äººåijĺ
    -0.07
    ulli
    -0.07
    POSITIVE LOGITS
    åĴĮåIJĮäºĭ
    0.09
     professionalism
    0.08
     tact
    0.08
    èģĮä¸ļéģĵå¾·
    0.08
    åħ¼ä»»
    0.08
    å°½èĩªå·±
    0.08
    æĿ¿ä¹¦
    0.08
    æ¯ıä¸Ģä½į
    0.08
     demeanor
    0.07
    ä¸İ客æĪ·
    0.07
    Activations Density 0.149%

    No Known Activations